AI Home Lab
Building an AI Home Lab — Part 1: Why I Stopped Treating AI as a Cloud Service
Why I built a hybrid AI home lab where local and cloud models work together as one engineering platform.
Weekly Articles
Practical product and engineering notes for business leaders.
Clear guidance on choosing sustainable technology, building the right product, and connecting business requirements to maintainable engineering systems.
More Writing
Follow my longer technical notes on Medium and LinkedIn.
Alongside this site, I publish practical articles on AI workflows, cloud architecture, automation, QA, product engineering, and technology leadership.
AI Home Lab
Building an AI Home Lab — Part 2: GGUF Switchboard: Bringing Kubernetes Thinking to Local LLMs
How GGUF Switchboard brings workload scheduling, memory-pressure eviction, and automatic model lifecycle management to local llama.cpp inference.
AI Home Lab
Building an AI Home Lab — Part 3: Operating an AI Platform
How Portainer, OmniRoute, Beszel, and Uptime Kuma turn a collection of local AI services into a platform I can operate reliably.
AI Home Lab
Building an AI Home Lab — Part 4: Local Project RAG: Giving AI the Context It Actually Needs
How a private Local Project RAG platform gives AI assistants persistent, searchable context across engineering projects without relying on cloud services.
AI Product Development
From Workshop to Working Product: How AI Agents Compress Digital Product Delivery
A practical workflow for designing and building digitization products with process workshops, mind maps, user stories, architecture, AI coding agents, MCP tools, and build discipline.
Forward Deployed Engineer
The Forward Deployed AI Engineer: One Person, the Entire Stack
How embedding a single engineer end-to-end eliminates translation loss and ships better enterprise AI applications — from requirements through design thinking, architecture, and production.
AI Strategy
AI Won't Fix a Broken Process — Here's What to Do First
Every operational business wants AI. Most are not ready for it. The problem is almost never the technology — it is what comes before it.
Technology Strategy
Five Signs You've Outgrown Your Current Tech Stack
Tech stacks age. If yours is slowing your team, killing your hiring, or making business decisions for you, it is time to take a hard look.
Fractional CTO
Hiring a Developer vs. Hiring a CTO: What's the Actual Difference?
Both write code. Only one is thinking about your business. Here is what separates a developer from a CTO — and why it matters before you hire.
Fractional CTO
From Requirements to Reliable Engineering
Why business leaders need a bridge from real requirements to proven, maintainable technology choices.
AI Strategy
Practical AI for Manufacturing and Non-IT Companies
A pragmatic way for operational businesses to adopt AI without creating brittle systems or expensive experiments.
LangChain
Python vs NestJS for LangChain: A Performance & Developer Experience Showdown
Should you build your LangChain service in Python or integrate it into a NestJS ecosystem? A comparison across performance, maintainability, hiring, and speed.
OpenAI
Resume Screening Bot with GPT + Google Sheets in Under 10 Minutes
A scalable, cloud-native resume skill-matching bot built with Google Apps Script, Google Sheets, and OpenAI, turning Sheets into a lightweight ATS.
LangChain
LangChain, Pinecone, and Me: Lessons from Integrating Vector Search into a Live Chat Product
How I used LangChain and Pinecone to turn a reactive chat assistant into a remembering, context-aware product, with lessons from production.
Kong
Setting Up Kong as an API Proxy with Docker Compose & Declarative Config
Deploy Kong as an API gateway in front of microservices using Docker Compose and Deck declarative config, with a bonus GitHub Actions workflow for Cloud Run.
Tailwind CSS
Downgrading from Tailwind CSS v4 to v3: A Hard-Earned Journey Back to Stability
After 48 hours of debugging broken layouts and purged classes in a Next.js app, here's what went wrong with Tailwind v4 and how we rolled back to v3.3.5.
Firebase
Guide to Integrating Microsoft Login to Next.js with TypeScript
Step-by-step guide to integrating Microsoft login with Firebase Auth in a Next.js + TypeScript app, including Azure/Entra setup, code, and troubleshooting.
QA Automation
Embracing Python + Pytest or Selenium in QA Automation: A Game-Changer for Development Speed and Efficiency
Why moving QA automation from Java to Python delivered a major boost in development speed, plus the Python testing ecosystem worth knowing.
Next.js
Next.js + TypeScript File Upload Using API with Formidable, and the 5 Lines That Changed Everything
After three days of debugging file uploads in a Next.js API route, the fix turned out to be five lines that disable the default bodyParser.
OSM
How to Get Statistics from OpenStreetMap Data
A guide to parsing and analysing OSM PBF data using Python and Osmium, extracting node/way/relation counts, way distances, and intersection stats.
Fine Tuning
Fine-Tuning Large Language Models (LLMs) for Chatbot Excellence
Why general-purpose LLMs fall short on domain-specific tasks, how fine-tuning fixes it, and the open-source LLMTrainingTools repo for building Q&A datasets.